Prune backups by retention

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true and idempotentHint=true, so the description is not required to repeat those. However, it adds little beyond the basic action: it mentions the prune schedule format and version requirement but does not disclose that the tool permanently deletes backups, what the response looks like, or any side effects. Given the annotations carry the safety profile, the description is adequate but not richly transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that clearly communicates the core action with an example. Every word is purposeful; no redundancy or fluff. It is optimally concise for an AI agent to quickly grasp the tool's function.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having annotations, the description lacks important context: it does not mention that the tool deletes old backups permanently (only inferred from destructiveHint), nor does it explain prerequisites (e.g., pool must exist), side effects, or return value (no output schema exists). For a destructive tool, more guidance on expected outcomes and potential risks is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for all three parameters. The description's example of the prune_backups parameter matches the schema's example, adding no new information. It does not explain the optional 'type' parameter or clarify that 'storage' must reference an existing pool. Since the schema already documents parameters, the description provides minimal added semantic value, scoring at the baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action: 'Apply a prune schedule ... to a storage pool'. It specifies the verb (apply), resource (storage pool), and provides an example of the prune options. It distinguishes from sibling tools like delete_backup (individual deletion) and run_backup_job (create backups) by focusing on retention-based pruning. The version requirement (Proxmox 8+) adds specificity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when a retention policy needs to be applied, but it does not explicitly state when to use this tool versus alternatives like delete_backup or create_backup_job. No exclusion criteria or context for when not to use it are provided. With many sibling backup tools, explicit guidance would improve the score.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.